Algorithmes et outils informatiques
On the Christoffel function and classification in data analysis
Comptes Rendus. Mathématique, Tome 360 (2022) no. G8, pp. 919-928.

Nous montrons que la fonction de Christoffel empirique associée à un échantillon fini de points peut fournir un outil simple pour la classification supervisée en analyse de données, avec de bonnes propriétés de généralisation.

We show that the empirical Christoffel function associated with a cloud of finitely many points sampled from a distribution, can provide a simple tool for supervised classification in data analysis, with good generalization properties.

Reçu le :
Révisé le :
Accepté le :
Publié le :
DOI : 10.5802/crmath.358
Classification : 41A30, 42C05, 47B32, 68T09, 94A16
Lasserre, Jean B. 1

1 LAAS-CNRS and Institute of Mathematics, BP 54200, 7 Avenue du Colonel Roche, 31031 Toulouse cédex 4, France
@article{CRMATH_2022__360_G8_919_0,
     author = {Lasserre, Jean B.},
     title = {On the {Christoffel} function and classification in data analysis},
     journal = {Comptes Rendus. Math\'ematique},
     pages = {919--928},
     publisher = {Acad\'emie des sciences, Paris},
     volume = {360},
     number = {G8},
     year = {2022},
     doi = {10.5802/crmath.358},
     language = {en},
     url = {http://www.numdam.org/articles/10.5802/crmath.358/}
}
TY  - JOUR
AU  - Lasserre, Jean B.
TI  - On the Christoffel function and classification in data analysis
JO  - Comptes Rendus. Mathématique
PY  - 2022
SP  - 919
EP  - 928
VL  - 360
IS  - G8
PB  - Académie des sciences, Paris
UR  - http://www.numdam.org/articles/10.5802/crmath.358/
DO  - 10.5802/crmath.358
LA  - en
ID  - CRMATH_2022__360_G8_919_0
ER  - 
%0 Journal Article
%A Lasserre, Jean B.
%T On the Christoffel function and classification in data analysis
%J Comptes Rendus. Mathématique
%D 2022
%P 919-928
%V 360
%N G8
%I Académie des sciences, Paris
%U http://www.numdam.org/articles/10.5802/crmath.358/
%R 10.5802/crmath.358
%G en
%F CRMATH_2022__360_G8_919_0
Lasserre, Jean B. On the Christoffel function and classification in data analysis. Comptes Rendus. Mathématique, Tome 360 (2022) no. G8, pp. 919-928. doi : 10.5802/crmath.358. http://www.numdam.org/articles/10.5802/crmath.358/

[1] Brunton, Steven L.; Kutz, J. Nathan Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control, Cambridge University Press, 2019 | DOI

[2] Lasserre, Jean Bernard; Pauwels, Edouard Sorting out typicality via the inverse moment matrix SOS polynomial, Advances in Neural Information Processing Systems, Curran Associates, Inc. (2016), pp. 190-198

[3] Lasserre, Jean Bernard; Pauwels, Edouard The empirical Christoffel function with applications in data analysis, Adv. Comput. Math., Volume 45 (2019) no. 3, pp. 1439-1468 | DOI | MR | Zbl

[4] Lasserre, Jean Bernard; Pauwels, Edouard; Putinar, Mihai The Christoffel–Darboux Kernel for Data Analysis, Cambridge Monographs on Applied and Computational Mathematics, 38, Cambridge University Press, 2022 | DOI | Zbl

[5] Marx, Swann; Pauwels, Edouard; Weisser, Tillmann; Henrion, Didier; Lasserre, Jean Bernard Semi-algebraic approximation using Christoffel–Darboux kernel, Constr. Approx., Volume 54 (2021) no. 3, pp. 391-429 | DOI | MR | Zbl

Cité par Sources :